The EVcouplings Python framework for coevolutionary sequence analysis

Hopf, Thomas A.; Green, Anna G.; Schubert, Benjamin; Mersmann, Sophia; Schaerfe, Charlotta P. I.; Ingraham, John L.; Tóth-Petróczy, Ágnes; Brock, Kelly; Riesselman, Adam J.; Kang, Chan; Dallago, Christian; Sander, Chris; Marks, Debora S.

doi:10.1101/326918

Cited by 67 publications

(112 citation statements)

References 25 publications

Supporting

Mentioning

111

Contrasting

Order By: Relevance

“…There were three evolutionary covariation methods taking into consideration IMPContact, namely, ELSC [40], MI [41], and OMES [42]. In spite of the many similar methods providing computational tools, e.g., EVFOLD [43], which obtained an even higher accuracy on covariation, those 3 methods are more convenient to realize an easy-to-use particular IHRC method for the users. For the purpose of discovering the covariation residue pairs from the multiple alignment result, ELSC (Explicit Likelihood of Subset Covariation) uses combinatorial arguments to realize a perturbative algorithm [44].…”

Section: Resultsmentioning

confidence: 99%

IMPContact: An Interhelical Residue Contact Prediction Method

Fang

Jia

et al. 2020

BioMed Research International

View full text Add to dashboard Cite

As an important category of proteins, alpha-helix transmembrane proteins (αTMPs) play an important role in various biological activities. Because the solved αTMP structures are inadequate, predicting the residue contacts among the transmembrane segments of an αTMP exhibits the basis of protein fold, which can be used to further discover more protein functions. A few efforts have been devoted to predict the interhelical residue contact using machine learning methods based on the prior knowledge of transmembrane protein structure. However, it is still a challenge to improve the prediction accuracy, while the deep learning method provides an opportunity to utilize the structural knowledge in a different insight. For this purpose, we proposed a novel αTMP residue-residue contact prediction method IMPContact, in which a convolutional neural network (CNN) was applied to recognize those interhelical contacts in a TMP using its specific structural features. There were four sequence-based TMP-specific features selected to descript a pair of residues, namely, evolutionary covariation, predicted topology structure, residue relative position, and evolutionary conservation. An up-to-date dataset was used to train and test the IMPContact; our method achieved better performance compared to peer methods. In the case studies, IHRCs in the regular transmembrane helixes were better predicted than in the irregular ones.

show abstract

Section: Resultsmentioning

confidence: 99%

IMPContact: An Interhelical Residue Contact Prediction Method

Fang

Jia

et al. 2020

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…We will also consider permanently including "coevolution-based" features into our algorithm, by either querying DBs of precomputed scores, as done with EVmutation, or by implementing interfaces to external libraries for Direct Coupling Analysis (DCA) [EVcouplings (Hopf et al, 2018), PconsC4 (Michel et al, 2018), Gremlin (Ovchinnikov et al, 2014), plmDCA (Ekeberg et al, 2014)]. A direct implementation would allow for much more flexibility in both fine-tuning the feature definitions, for instance by introducing normalizations that were shown to improve their predictive power (Feinauer and Weigt, 2017), and in the selection of MSAs for DCA calculations.…”

Section: Discussionmentioning

confidence: 99%

Rhapsody: Pathogenicity prediction of human missense variants based on protein sequence, structure and dynamics

Ponzoni

Oltvai

Bahar

2019

Preprint

View full text Add to dashboard Cite

AbstractThe biological effects of human missense variants have been studied experimentally for decades but predicting their effects in clinical molecular diagnostics remains challenging. Available computational tools are usually based on the analysis of sequence conservation and structural properties of the mutant protein. We recently introduced a new machine learning method that demonstrated for the first time the significance of protein dynamics in determining the pathogenicity of missense variants. Here we present a significant extension that integrates coevolutionary data from Pfam database and we also introduce a new interface (Rhapsody) that enables fully automated assessment of pathogenicity. Benchmarked against a dataset of about 20,000 annotated variants, the methodology is shown to outperform well-established and/or advanced prediction tools. We illustrate the utility of our approach by in silico saturation mutagenesis study of human H-Ras. The tool is made available both as a webtool (rhapsody.csb.pitt.edu) and an open source Python package (pip install prody-rhapsody).

show abstract

“…We resorted to an unsupervised method for predicting the mutation effects that specifically captures residue dependencies between positions. On Python 3 we deployed EVcoupling to assess the quantitative effects of mutations in RBD (23). Deep mutational scan was performed to understand the effects of substitution mutations in RBD and generate the mutational landscape.…”

Section: …… (2)mentioning

confidence: 99%

“…Z is to normalize the distribution to sum to one over all possible sequences of a fixed length. E(σ) was represented as (negative) energy of a model from statistical physics or as proportional to the scaled fitness N e F in toy, equilibrium models of population genetics (23). We used the energy function E(σ) with two types of constraints viz.…”

Section: …… (2)mentioning

confidence: 99%

An exploration of the SARS-CoV-2 spike receptor binding domain (RBD) – a complex palette of evolutionary and structural features

Sanyal

Chowdhury

Uversky

et al. 2020

Preprint

View full text Add to dashboard Cite

SARS-CoV-2 spike protein (S) is associated with the entry of virus inside the host cell by recruiting its loop dominant receptor binding domain (RBD) and interacting with the host ACE2 receptor. Our study deploying a two-tier approach encompassing evolutionary and structural analysis provides a comprehensive picture of the RBD, which could be of potential use for better understanding the RBD and address its druggability issues. Resorting to an ensemble of sequence space exploratory tools including co-evolutionary analysis and deep mutational scans we provide a quantitative insight into the evolutionarily constrained subspace of the RBD sequence space. Guided by structure network analysis and Monte Carlo simulation we highlight regions inside the RBD, which are critical for providing structural integrity and conformational flexibility of the binding cleft. We further deployed fuzzy C-means clustering by plugging the evolutionary and structural features of discrete structure blocks of RBD to understand which structure blocks share maximum overlap based on their evolutionary and structural features. Deploying this multi-tier interlinked approach, which essentially distilled the evolutionary and structural features of RBD, we highlight discrete region, which could be a potential druggable pocket thereby destabilizing the structure and addressing evolutionary routes.

show abstract

The EVcouplings Python framework for coevolutionary sequence analysis

Cited by 67 publications

References 25 publications

IMPContact: An Interhelical Residue Contact Prediction Method

IMPContact: An Interhelical Residue Contact Prediction Method

Rhapsody: Pathogenicity prediction of human missense variants based on protein sequence, structure and dynamics

An exploration of the SARS-CoV-2 spike receptor binding domain (RBD) – a complex palette of evolutionary and structural features

Contact Info

Product

Resources

About